Update app.py

app.py

@@ -4,7 +4,7 @@ import pandas as pd
 from sqlalchemy import create_engine
 from langchain.chat_models import ChatOpenAI
 from langchain.utilities.sql_database import SQLDatabase
-from langchain.tools.sql.toolkit import SQLDatabaseToolkit
+from langchain.chains import SQLDatabaseChain
 
 # Set OpenAI API Key
 openai.api_key = "sk-O7esHSo2XAWm-GXUGXp7_P9l4qXrQMn0CIGzs34ojLT3BlbkFJeXGSSvywppRTAvyT0zZkmZLZsj5cg7XkAkBTh8ZxoA"
@@ -16,7 +16,7 @@ engine = create_engine(DATABASE_URL)
 # Set up LangChain components
 llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0.5)  # OpenAI's Chat model for LLM
 db = SQLDatabase(engine)  # Connect LangChain to the database
-toolkit = SQLDatabaseToolkit(llm=llm, db=db)  # Create the SQL toolkit
+sql_chain = SQLDatabaseChain.from_llm(llm, database=db)  # Create the SQL chain
 
 # Streamlit UI setup
 st.title("SQL Data Chatbot with LangChain")
@@ -27,22 +27,18 @@ user_question = st.text_input("Your question:")
 
 # Process the question if provided
 if user_question:
-    # Generate the SQL query and answer using the toolkit
+    # Generate the SQL query and answer using the SQL chain
     try:
-        # Execute the question through the SQL toolkit
-        answer = toolkit.query(user_question)
+        # Execute the question through the SQL chain
+        response = sql_chain.run(user_question)
 
         # Display the generated SQL query and answer
-        st.subheader("Generated SQL Query")
-        st.code(answer.query, language="sql")
-
-        # Display the generated answer
-        st.subheader("Answer")
-        st.write(answer.result)
+        st.subheader("Generated SQL Query and Answer")
+        st.write(response)
 
         # Execute the SQL query to get results
         with engine.connect() as conn:
-            result_df = pd.read_sql_query(answer.query, conn)
+            result_df = pd.read_sql_query(response.query, conn)
 
         # Show query results if any
         if not result_df.empty: